#### Filter Results:

#### Publication Year

1991

2016

#### Publication Type

#### Co-author

#### Key Phrase

#### Publication Venue

#### Data Set Used

Learn More

Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. Two different multi-plicative algorithms for NMF are analyzed. They differ only slightly in the multiplicative factor used in the update rules. One algorithm can be shown to minimize the conventional least squares error while the other… (More)

We propose an algorithm called <italic>query by commitee</italic>, in which a committee of students is trained on the same data set. The next query is chosen according to the <italic>principle of maximal disagreement</italic>. The algorithm is studied for two toy models: the high-low game and perceptron learning of another perceptron. As the number of… (More)

We analyze the " query by committee " algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential… (More)

We analyze the conditions under which synaptic learning rules based on action potential timing can be approximated by learning rules based on firing rates. In particular, we consider a form of plasticity in which synapses depress when a presynaptic spike is followed by a postsynaptic spike, and potentiate with the opposite temporal ordering. Such… (More)

We analyze the "query by committee" algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease… (More)

A simple but powerful modification of the standard Gaussian distribution is studied. The variables of the rectified Gaussian are constrained to be nonnegative, enabling the use of nonconvex energy functions. Two multimodal examples, the competitive and cooperative distributions, illustrate the representational power of the rectified Gaussian. Since the… (More)

- Viren Jain, Benjamin Bollmann, Mark Richardson, Daniel R. Berger, Moritz Helmstaedter, Kevin L. Briggman +11 others
- CVPR
- 2010

Recent studies have shown that machine learning can improve the accuracy of detecting object boundaries in images. In the standard approach, a boundary detector is trained by minimizing its pixel-level disagreement with human boundary tracings. This naive metric is problematic because it is overly sensitive to boundary locations. This problem is solved by… (More)

In this paper we introduce and investigate a mathematically rigorous theory of learning curves that is based on ideas from statistical mechanics. The advantage of our theory over the well-established Vapnik-Chervonenkis theory is that our bounds can be considerably tighter in many cases, and are also more reflective of the true behavior (functional form) of… (More)

It is often assumed that learning takes place by changing an otherwise stable neural representation. To test this assumption, we studied changes in the directional tuning of primate motor cortical neurons during reaching movements performed in familiar and novel environments. During the familiar task, tuning curves exhibited slow random drift. During… (More)

- Jinseop S. Kim, Matthew J. Greene, Aleksandar Zlateski, Kisuk Lee, Mark Richardson, Srinivas C. Turaga +7 others
- Nature
- 2014

How does the mammalian retina detect motion? This classic problem in visual neuroscience has remained unsolved for 50 years. In search of clues, here we reconstruct Off-type starburst amacrine cells (SACs) and bipolar cells (BCs) in serial electron microscopic images with help from EyeWire, an online community of 'citizen neuroscientists'. On the basis of… (More)